Replacing pooling functions in Convolutional Neural Networks by linear combinations of increasing functions

Traditionally, Convolutional Neural Networks make use of the maximum or arithmetic mean in order to reduce the features extracted by convolutional layers in a downsampling process known as pooling. However, there is no strong argument to settle upon one of the two functions and, in practice, this se...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks 2022-08, Vol.152, p.380-393
Hauptverfasser:	Rodriguez-Martinez, Iosu, Lafuente, Julio, Santiago, Regivan H.N., Dimuro, Graçaliz Pereira, Herrera, Francisco, Bustince, Humberto
Format:	Artikel
Sprache:	eng
Schlagworte:	Convolutional Neural Networks Generalized Sugeno integral Order statistic Pooling function
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!